On 6/3/25 10:22 AM, Terry Bowman wrote:
> CXL protocol errors are not enabled for all CXL devices after boot. These
> must be enabled inorder to process CXL protocol errors.
>
> Export the AER service driver's pci_aer_unmask_internal_errors().
>
> Introduce cxl_unmask_prot_interrupts() to call pci_aer_unmask_internal_errors().
> pci_aer_unmask_internal_errors() expects the pdev->aer_cap is initialized.
> But, dev->aer_cap is not initialized for CXL Upstream Switch Ports and CXL
> Downstream Switch Ports. Initialize the dev->aer_cap if necessary. Enable AER
> correctable internal errors and uncorrectable internal errors for all CXL
> devices.
>
> Signed-off-by: Terry Bowman <terry.bowman@amd.com>
> Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
> ---
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
> drivers/cxl/port.c | 29 +++++++++++++++++++++++++++--
> drivers/pci/pcie/aer.c | 3 ++-
> include/linux/aer.h | 1 +
> 3 files changed, 30 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/cxl/port.c b/drivers/cxl/port.c
> index 0f7c4010ba58..3687848ae772 100644
> --- a/drivers/cxl/port.c
> +++ b/drivers/cxl/port.c
> @@ -3,6 +3,7 @@
> #include <linux/device.h>
> #include <linux/module.h>
> #include <linux/slab.h>
> +#include <linux/pci.h>
>
> #include "cxlmem.h"
> #include "cxlpci.h"
> @@ -60,6 +61,21 @@ static int discover_region(struct device *dev, void *unused)
>
> #ifdef CONFIG_PCIEAER_CXL
>
> +static void cxl_unmask_prot_interrupts(struct device *dev)
> +{
> + struct pci_dev *pdev __free(pci_dev_put) =
> + pci_dev_get(to_pci_dev(dev));
> +
> + if (!pdev->aer_cap) {
> + pdev->aer_cap = pci_find_ext_capability(pdev,
> + PCI_EXT_CAP_ID_ERR);
> + if (!pdev->aer_cap)
> + return;
> + }
> +
> + pci_aer_unmask_internal_errors(pdev);
> +}
> +
> static void cxl_dport_map_rch_aer(struct cxl_dport *dport)
> {
> resource_size_t aer_phys;
> @@ -118,8 +134,12 @@ static void cxl_uport_init_ras_reporting(struct cxl_port *port,
>
> map->host = host;
> if (cxl_map_component_regs(map, &port->uport_regs,
> - BIT(CXL_CM_CAP_CAP_ID_RAS)))
> + BIT(CXL_CM_CAP_CAP_ID_RAS))) {
> dev_dbg(&port->dev, "Failed to map RAS capability\n");
> + return;
> + }
> +
> + cxl_unmask_prot_interrupts(port->uport_dev);
> }
>
> /**
> @@ -144,9 +164,12 @@ void cxl_dport_init_ras_reporting(struct cxl_dport *dport, struct device *host)
> }
>
> if (cxl_map_component_regs(&dport->reg_map, &dport->regs.component,
> - BIT(CXL_CM_CAP_CAP_ID_RAS)))
> + BIT(CXL_CM_CAP_CAP_ID_RAS))) {
> dev_dbg(dport->dport_dev, "Failed to map RAS capability\n");
> + return;
> + }
>
> + cxl_unmask_prot_interrupts(dport->dport_dev);
> }
> EXPORT_SYMBOL_NS_GPL(cxl_dport_init_ras_reporting, "CXL");
>
> @@ -177,6 +200,8 @@ static void cxl_endpoint_port_init_ras(struct cxl_port *port)
> }
>
> cxl_dport_init_ras_reporting(dport, &cxlmd->dev);
> +
> + cxl_unmask_prot_interrupts(cxlmd->cxlds->dev);
> }
>
> #else
> diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
> index 5efe5a718960..2d202ad1453a 100644
> --- a/drivers/pci/pcie/aer.c
> +++ b/drivers/pci/pcie/aer.c
> @@ -964,7 +964,7 @@ static bool find_source_device(struct pci_dev *parent,
> * Note: AER must be enabled and supported by the device which must be
> * checked in advance, e.g. with pcie_aer_is_native().
> */
> -static void pci_aer_unmask_internal_errors(struct pci_dev *dev)
> +void pci_aer_unmask_internal_errors(struct pci_dev *dev)
> {
> int aer = dev->aer_cap;
> u32 mask;
> @@ -977,6 +977,7 @@ static void pci_aer_unmask_internal_errors(struct pci_dev *dev)
> mask &= ~PCI_ERR_COR_INTERNAL;
> pci_write_config_dword(dev, aer + PCI_ERR_COR_MASK, mask);
> }
> +EXPORT_SYMBOL_NS_GPL(pci_aer_unmask_internal_errors, "CXL");
>
> static bool is_cxl_mem_dev(struct pci_dev *dev)
> {
> diff --git a/include/linux/aer.h b/include/linux/aer.h
> index c9a18eca16f8..74600e75705f 100644
> --- a/include/linux/aer.h
> +++ b/include/linux/aer.h
> @@ -107,5 +107,6 @@ void pci_print_aer(struct pci_dev *dev, int aer_severity,
> int cper_severity_to_aer(int cper_severity);
> void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn,
> int severity, struct aer_capability_regs *aer_regs);
> +void pci_aer_unmask_internal_errors(struct pci_dev *dev);
> #endif //_AER_H_
>
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer